Papers with latent states representations - vectors

1 papers
HypMix: Hyperbolic Interpolative Data Augmentation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for data augmentation involve performing mathematical operations over the raw input samples or their latent states representations, but these operations are performed in the Euclidean space, simplifying these representations and resulting in noisy interpolations.
Approach: They propose a model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space that captures the complex geometry of input and hidden state hierarchies better than its contemporaries.
Outcome: The proposed technique outperforms state-of-the-art methods on benchmark and low resource datasets across speech, text, and vision modalities.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations